私がそれをした一つの方法：
- 一度にサンプルのブロックを読み取る、たとえば0.05秒の価値がある
- RMSブロックの振幅（個々のサンプルの二乗の平均の平方根）を計算します）
- ブロックのRMS振幅がしきい値より大きい場合、それは「ノイズの多いブロック」です。それ以外の場合、それは「静かなブロック」です。
- 突然タップすると、静かなブロックに続いて少数のノイズの多いブロックが続き、その後静かなブロックになります
- 静かなブロックが得られない場合は、しきい値が低すぎます
- ノイズの多いブロックが表示されない場合は、しきい値が高すぎます
私のアプリケーションは「興味深い」ノイズを無人で記録していたので、ノイズの多いブロックが存在する限り記録していました。 15秒間のノイズのある期間（「耳を覆う」）がある場合は、しきい値に1.1を掛け、15の場合はしきい値を0.9に掛けます分静かな期間（「聞くのが難しい」） ）。アプリケーションにはさまざまなニーズがあります。
また、観察されたRMS=値に関する私のコードのコメントに気づきました。MacbookProの内蔵マイクでは、+ /-1.0の正規化されたオーディオデータ範囲で、入力ボリュームが最大に設定されています。いくつかのデータポイント：
- 私の家にある不愉快に大きな中央暖房ファン0.003-0.006（-50dBから-44dB）
- 同じラップトップで0.010-0.40（-40dB〜-8dB）タイピング
- 0.10（-20dB）1 'の距離で指を柔らかくスナップ
- 0.60（-4.4dB）1 'で指を大音量でスナップ
更新：開始するためのサンプルを以下に示します。
#!/usr/bin/python
# open a microphone in pyAudio and listen for taps
import pyaudio
import struct
import math
INITIAL_TAP_THRESHOLD = 0.010
FORMAT = pyaudio.Paint16
SHORT_NORMALIZE = (1.0/32768.0)
CHANNELS = 2
RATE = 44100
INPUT_BLOCK_TIME = 0.05
INPUT_FRAMES_PER_BLOCK = int(RATE*INPUT_BLOCK_TIME)
# if we get this many noisy blocks in a row, increase the threshold
OVERSENSITIVE = 15.0/INPUT_BLOCK_TIME
# if we get this many quiet blocks in a row, decrease the threshold
UNDERSENSITIVE = 120.0/INPUT_BLOCK_TIME
# if the noise was longer than this many blocks, it's not a 'tap'
MAX_TAP_BLOCKS = 0.15/INPUT_BLOCK_TIME
def get_rms( block ):
# RMS amplitude is defined as the square root of the
# mean over time of the square of the amplitude.
# so we need to convert this string of bytes into
# a string of 16-bit samples...
# we will get one short out for each
# two chars in the string.
count = len(block)/2
format = "%dh"%(count)
shorts = struct.unpack( format, block )
# iterate over the block.
sum_squares = 0.0
for sample in shorts:
# sample is a signed short in +/- 32768.
# normalize it to 1.0
n = sample * SHORT_NORMALIZE
sum_squares += n*n
return math.sqrt( sum_squares / count )
class TapTester(object):
def __init__(self):
self.pa = pyaudio.PyAudio()
self.stream = self.open_mic_stream()
self.tap_threshold = INITIAL_TAP_THRESHOLD
self.noisycount = MAX_TAP_BLOCKS+1
self.quietcount = 0
self.errorcount = 0
def stop(self):
self.stream.close()
def find_input_device(self):
device_index = None
for i in range( self.pa.get_device_count() ):
devinfo = self.pa.get_device_info_by_index(i)
print( "Device %d: %s"%(i,devinfo["name"]) )
for keyword in ["mic","input"]:
if keyword in devinfo["name"].lower():
print( "Found an input: device %d - %s"%(i,devinfo["name"]) )
device_index = i
return device_index
if device_index == None:
print( "No preferred input found; using default input device." )
return device_index
def open_mic_stream( self ):
device_index = self.find_input_device()
stream = self.pa.open( format = FORMAT,
channels = CHANNELS,
rate = RATE,
input = True,
input_device_index = device_index,
frames_per_buffer = INPUT_FRAMES_PER_BLOCK)
return stream
def tapDetected(self):
print("Tap!")
def listen(self):
try:
block = self.stream.read(INPUT_FRAMES_PER_BLOCK)
except IOError as e:
# dammit.
self.errorcount += 1
print( "(%d) Error recording: %s"%(self.errorcount,e) )
self.noisycount = 1
return
amplitude = get_rms( block )
if amplitude > self.tap_threshold:
# noisy block
self.quietcount = 0
self.noisycount += 1
if self.noisycount > OVERSENSITIVE:
# turn down the sensitivity
self.tap_threshold *= 1.1
else:
# quiet block.
if 1 <= self.noisycount <= MAX_TAP_BLOCKS:
self.tapDetected()
self.noisycount = 0
self.quietcount += 1
if self.quietcount > UNDERSENSITIVE:
# turn up the sensitivity
self.tap_threshold *= 0.9
if __name__ == "__main__":
tt = TapTester()
for i in range(1000):
tt.listen()
上記のコードの簡略版...
import pyaudio
import struct
import math
INITIAL_TAP_THRESHOLD = 0.010
FORMAT = pyaudio.Paint16
SHORT_NORMALIZE = (1.0/32768.0)
CHANNELS = 2
RATE = 44100
INPUT_BLOCK_TIME = 0.05
INPUT_FRAMES_PER_BLOCK = int(RATE*INPUT_BLOCK_TIME)
OVERSENSITIVE = 15.0/INPUT_BLOCK_TIME
UNDERSENSITIVE = 120.0/INPUT_BLOCK_TIME # if we get this many quiet blocks in a row, decrease the threshold
MAX_TAP_BLOCKS = 0.15/INPUT_BLOCK_TIME # if the noise was longer than this many blocks, it's not a 'tap'
def get_rms(block):
# RMS amplitude is defined as the square root of the
# mean over time of the square of the amplitude.
# so we need to convert this string of bytes into
# a string of 16-bit samples...
# we will get one short out for each
# two chars in the string.
count = len(block)/2
format = "%dh"%(count)
shorts = struct.unpack( format, block )
# iterate over the block.
sum_squares = 0.0
for sample in shorts:
# sample is a signed short in +/- 32768.
# normalize it to 1.0
n = sample * SHORT_NORMALIZE
sum_squares += n*n
return math.sqrt( sum_squares / count )
pa = pyaudio.PyAudio() #]
#|
stream = pa.open(format = FORMAT, #|
channels = CHANNELS, #|---- You always use this in pyaudio...
rate = RATE, #|
input = True, #|
frames_per_buffer = INPUT_FRAMES_PER_BLOCK) #]
tap_threshold = INITIAL_TAP_THRESHOLD #]
noisycount = MAX_TAP_BLOCKS+1 #|---- Variables for noise detector...
quietcount = 0 #|
errorcount = 0 #]
for i in range(1000):
try: #]
block = stream.read(INPUT_FRAMES_PER_BLOCK) #|
except IOError, e: #|---- just in case there is an error!
errorcount += 1 #|
print( "(%d) Error recording: %s"%(errorcount,e) ) #|
noisycount = 1 #]
amplitude = get_rms(block)
if amplitude > tap_threshold: # if its to loud...
quietcount = 0
noisycount += 1
if noisycount > OVERSENSITIVE:
tap_threshold *= 1.1 # turn down the sensitivity
else: # if its to quiet...
if 1 <= noisycount <= MAX_TAP_BLOCKS:
print 'tap!'
noisycount = 0
quietcount += 1
if quietcount > UNDERSENSITIVE:
tap_threshold *= 0.9 # turn up the sensitivity